eugene1g/agent-safehouse
Sandbox your local AI agents so they can read/write only what they need
Enforces fine-grained file and integration access using macOS `sandbox-exec` with composable policy profiles and automatic symlink resolution for system paths. Built-in profiles for Claude, Codex, and other coding agents provide deny-first defaults while supporting machine-specific overrides through appended policies and Git worktree auto-detection. Integrates with shell environments and local configuration to sandbox agent processes with minimal friction to normal development workflows.
1,184 stars. Actively maintained with 108 commits in the last 30 days.
Stars
1,184
Forks
40
Language
Shell
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
108
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/eugene1g/agent-safehouse"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related agents
e2b-dev/E2B
Open-source, secure environment with real-world tools for enterprise-grade agents.
alibaba/OpenSandbox
OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language...
e2b-dev/infra
Infrastructure that's powering E2B Cloud.
boxlite-ai/boxlite
Sandboxes for every agent. Embeddable, stateful, snapshots, and hardware isolation.
always-further/nono
Secure, kernel-enforced sandbox CLI and SDKs for AI agents. Capability-based isolation with...